相关论文: DV-SFT: Direct Vision Supervision for Fine-Grained…

In recent times, the standard practice for developing MLLMs is to feed features from vision encoder(s) into the LLM and train with natural language supervision. This approach often causes models to lean towards language comprehension and…

Masked image modeling (MIM) has emerged as a promising approach for pre-training Vision Transformers (ViTs). MIMs predict masked tokens token-wise to recover target signals that are tokenized from images or generated by pre-trained models…

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in…

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…

Unsupervised pre-training on millions of digital-born or scanned documents has shown promising advances in visual document understanding~(VDU). While various vision-language pre-training objectives are studied in existing solutions, the…

Speculative decoding significantly accelerates language model inference by enabling a lightweight draft model to propose multiple tokens that a larger target model verifies simultaneously. However, applying this technique to vision-language…

Self-Supervised Learning (SSL) is a valuable and robust training methodology for contemporary Deep Neural Networks (DNNs), enabling unsupervised pretraining on a 'pretext task' that does not require ground-truth labels/annotation. This…

Traditional Shot Boundary Detection (SBD) inherently struggles with complex transitions by formulating the task around isolated cut points, frequently yielding corrupted video shots. We address this fundamental limitation by formalizing the…

Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of…

Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its…

Large Vision-Language Models (LVLMs) generate contextually relevant responses by jointly interpreting visual and textual inputs. However, our finding reveals they often mistakenly perceive text inputs lacking visual evidence as being part…

Large vision-language models (VLMs) enable joint processing of text and images. However, incorporating vision data significantly increases the prompt length, resulting in a longer time to first token (TTFT). This bottleneck can be…

Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM image encoders map fixed-size images to a fixed number of…

Defending pre-trained vision-language models (VLMs), such as CLIP, against adversarial attacks is crucial, as these models are widely used in diverse zero-shot tasks, including image classification. However, existing adversarial training…

Scene text recognition (STR) enables computers to recognize and read the text in various real-world scenes. Recent STR models benefit from taking linguistic information in addition to visual cues into consideration. We propose a novel…

Vision-and-language navigation requires an agent to navigate through a real 3D environment following natural language instructions. Despite significant advances, few previous works are able to fully utilize the strong correspondence between…

Multimodal large language models (MLLMs) demand considerable computations for inference due to the extensive parameters and the additional input tokens needed for visual information representation. Herein, we introduce Visual Tokens…

Open-source multimodal large language models (MLLMs) excel in various tasks involving textual and visual inputs but still struggle with complex multimodal mathematical reasoning, lagging behind proprietary models like GPT-4V(ision) and…

Vision-Language Models (VLMs) excel at 2D tasks such as grounding and captioning, yet remain limited in 3D understanding. A key limitation is their text-only supervision paradigm, which under-constrains fine-grained visual perception and…

Vision-Language Models (VLMs) demand substantial computational resources during inference, largely due to the extensive visual input tokens for representing visual information. Previous studies have noted that visual tokens tend to receive…